透明化模型决策过程能否减少用户对算法的抵触？
Overcoming Algorithm Aversion with Transparency: Can Transparent Predictions Change User Behavior?
- 引入可视化解释的可解释模型，观察用户行为变化
- 允许用户调整预测能有效降低算法抵触感
- 透明度效果不显著，与可调性独立作用
已有研究表明，允许用户调整机器学习模型的预测可减轻对不完美算法决策的抵触。但这些研究均在用户无法获知模型推理过程的背景下进行。本文概念性复现一项经典研究，考察可调预测对算法抵触的影响，并进一步引入一个能可视化展示决策逻辑的可解释模型。通过一项预先注册的用户研究（280名参与者），我们探究透明度与可调性在降低算法决策抵触中的交互作用。结果复现了可调性效应：允许用户修改预测可缓解抵触。然而，透明度的影响远小于预期且在本样本中不显著；透明度与可调性的效果更趋于独立而非协同。
原文摘要 · Abstract (English)
Previous work has shown that allowing users to adjust a machine learning (ML) model's predictions can reduce aversion to imperfect algorithmic decisions. However, these results were obtained in situations where users had no information about the model's reasoning. Thus, it remains unclear whether interpretable ML models could further reduce algorithm aversion or even render adjustability obsolete. In this paper, we conceptually replicate a well-known study that examines the effect of adjustable predictions on algorithm aversion and extend it by introducing an interpretable ML model that visually reveals its decision logic. Through a pre-registered user study with 280 participants, we investigate how transparency interacts with adjustability in reducing aversion to algorithmic decision-making. Our results replicate the adjustability effect, showing that allowing users to modify algorithmic predictions mitigates aversion. Transparency's impact appears smaller than expected and was not significant for our sample. Furthermore, the effects of transparency and adjustability appear to be more independent than expected.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。